NanoGPT

TEE-only Gateway

Pay-per-prompt confidential inference — TEE-backed models with ECDSA per-request attestation

NanoGPT runs a curated set of open-source models inside Trusted Execution Environments (TEE), providing hardware-enforced confidentiality for prompts and responses. TEE models are identified by a TEE/ prefix and can be cryptographically verified: a dedicated attestation endpoint returns the hardware quote, and a per-request ECDSA signature endpoint lets clients confirm their specific completion was produced inside the enclave. No account or subscription required — anonymous cryptocurrency payments accepted.

Models 27

From $0.15/M input tokens

Organization roles Storefront · Aggregator

Advertised Channel TEE-only Gateway

API Features

OpenAI Compatible ✓

Streaming ✓

Function Calling —

Batch Inference —

Vision —

Embeddings —

Attestation Status

View full details →

Last checked: Aug 26, 2026, 3:01 AM

Model coverage: 27/27 current catalog models have an explicit check.

Explicit trust failures At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.

0 verified 16 partial 2 failed 9 unavailable

Hardware 2 bad TCB policy 2 bad Freshness 11 warning Channel binding Not shown Workload identity 27 warning Source provenance 27 warning Request route 27 warning Availability 9 warning

Hardware evidence failed 2 TCB policy failed 2 Workload identity not proven 18 Source provenance not proven 18

Get notified when this provider's attestation verdict changes: Alerts RSS

Models & Pricing

Model	Family	Context	Max Out	Input /M	Output /M	Free	Attestation	Observed route
Qwen3.8 27B	Qwen	4K	—	Custom	—	—	unreachable	Not identified
Qwen3.6 27B	Qwen	256K	—	$0.32	$2.70	—	partial	Not identified
GPT-OSS 120B	OpenAI GPT	128K	—	$2.00	$2.00	—	unreachable	Not identified
GPT-OSS 20B	OpenAI GPT	128K	—	$0.20	$0.80	—	partial	Not identified
Qwen2.5-VL 72B	Qwen	64K	—	$0.70	$0.70	—	partial	Not identified
DeepSeek V4 Flash	DeepSeek	4K	—	Custom	—	—	unreachable	Not identified
DeepSeek V3.2	DeepSeek	160K	—	$0.50	$1.00	—	partial	Not identified
Qwen3.6 35B A3B	Qwen	4K	—	Custom	—	—	partial	Not identified
Qwen3.6 35B A3B Uncensored	Qwen	128K	—	$0.30	$1.50	—	partial	Not identified
Qwen3.5 27B	Qwen	256K	—	$0.30	$2.40	—	failed	Not identified
Qwen3.5 397B A17B	Qwen	256K	—	$0.55	$3.50	—	unreachable	Not identified
Qwen3.5 122B A10B	Qwen	256K	—	$0.46	$3.68	—	partial	Not identified
Muse Glimmer 30B	Unknown	4K	—	Custom	—	—	partial	Not identified
Gemma 4 31B IT	Google Gemma	256K	—	$0.15	$0.46	—	partial	Not identified
Gemma 4 26B A4B Uncensored	Google Gemma	64K	—	$0.15	$0.70	—	partial	Not identified
Gemma 3 27B	Google Gemma	128K	—	$0.20	$0.80	—	partial	Not identified
Gemma 4 31B	Google Gemma	256K	—	$0.45	$1.00	—	unreachable	Not identified
Gemma 4 31B Thinking	Google Gemma	256K	—	$0.45	$1.00	—	unreachable	Not identified
Llama 3.3 70B	Meta Llama	125K	—	$2.00	$2.00	—	unreachable	Not identified
Kimi K3	Moonshot AI	4K	—	Custom	—	—	failed	Not identified
Kimi K2.6	Moonshot AI	4K	—	$1.50	$5.25	—	unreachable	Not identified
Kimi K2.7 Code	Moonshot AI	4K	—	Custom	—	—	partial	Not identified
GLM 4.7	ZhipuAI GLM	128K	—	$0.85	$3.30	—	partial	Not identified
GLM 5.1	ZhipuAI GLM	4K	—	$1.50	$5.25	—	unreachable	Not identified
GLM 5.1 Thinking	ZhipuAI GLM	4K	—	$1.50	$5.25	—	partial	Not identified
GLM 5.2	ZhipuAI GLM	4K	—	Custom	—	—	partial	Not identified
GLM 5.2 :Thinking	ZhipuAI GLM	4K	—	Custom	—	—	partial	Not identified